Add files using upload-large-folder tool

config.json

@@ -0,0 +1,192 @@
+{
+  "architectures": [
+    "OpenProvenceForSequenceClassification"
+  ],
+  "auto_map": {
+    "AutoConfig": "modeling_open_provence_standalone.OpenProvenceConfig",
+    "AutoModel": "modeling_open_provence_standalone.OpenProvenceForSequenceClassification",
+    "AutoModelForSequenceClassification": "modeling_open_provence_standalone.OpenProvenceForSequenceClassification",
+    "AutoModelForTokenClassification": "modeling_open_provence_standalone.OpenProvenceForTokenClassification"
+  },
+  "base_model_config": {
+    "_name_or_path": "Alibaba-NLP/gte-reranker-modernbert-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "ModernBertForSequenceClassification"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 50281,
+    "chunk_size_feed_forward": 0,
+    "classifier_activation": "gelu",
+    "classifier_bias": false,
+    "classifier_dropout": 0.0,
+    "classifier_pooling": "mean",
+    "cls_token_id": 50281,
+    "cross_attention_hidden_size": null,
+    "decoder_bias": true,
+    "decoder_start_token_id": null,
+    "deterministic_flash_attn": false,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dtype": "float32",
+    "early_stopping": false,
+    "embedding_dropout": 0.0,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50282,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "global_attn_every_n_layers": 3,
+    "global_rope_theta": 160000.0,
+    "gradient_checkpointing": false,
+    "hidden_activation": "gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0"
+    },
+    "initializer_cutoff_factor": 2.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1152,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "local_attention": 128,
+    "local_rope_theta": 10000.0,
+    "max_length": 20,
+    "max_position_embeddings": 8192,
+    "min_length": 0,
+    "mlp_bias": false,
+    "mlp_dropout": 0.0,
+    "model_type": "modernbert",
+    "no_repeat_ngram_size": 0,
+    "norm_bias": false,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 22,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 50283,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repad_logits_with_grad": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": 50282,
+    "sparse_pred_ignore_index": -100,
+    "sparse_prediction": false,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.57.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 50368
+  },
+  "base_model_name_or_path": "Alibaba-NLP/gte-reranker-modernbert-base",
+  "encoder_architecture": "modernbert",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_length": 512,
+  "mode": "reranking_pruning",
+  "model_type": "open_provence",
+  "num_pruning_labels": 2,
+  "pruning_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dtype": null,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "open_provence_head",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sentence_pooling": "mean",
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.57.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_weighted_pooling": false
+  },
+  "tokenizer_name_or_path": null,
+  "transformers_version": "4.57.1",
+  "vocab_size": 50368
+}

eval_results/eval_mldr.md

@@ -0,0 +1,19 @@
+# MLDR Evaluation Summary — open-provence-reranker-v1
+
+## English (en) — refreshed 2025-10-27
+
+| Threshold | Has Answer (1) | Has Answer (0) | Failed | Score Mean | Median | Min | Max | Process Time (s) | Eval Time (s) |
+| --- | ---:| ---:| ---:| ---:| ---:| ---:| ---:| ---:| ---:|
+| 0.1 | 164 | 10 | 0 | 0.9354 | 1.0000 | 0.0000 | 1.0000 | 249.06 | 43.89 |
+| 0.2 | 158 | 16 | 0 | 0.9025 | 1.0000 | 0.0000 | 1.0000 | 251.30 | 38.25 |
+| 0.3 | 161 | 13 | 0 | 0.9165 | 1.0000 | 0.0000 | 1.0000 | 260.52 | 34.87 |
+| 0.5 | 152 | 22 | 0 | 0.8645 | 1.0000 | 0.0000 | 1.0000 | 254.43 | 35.69 |
+
+### Original Text (no pruning)
+
+- Has Answer (1): 163
+- Has Answer (0): 11
+- Failed: 0
+- Answer score mean/median/min/max: 0.9328 / 1.0000 / 0.0000 / 1.0000
+- Process time (s): 4.27
+- LLM eval time (s): 227.76

eval_results/mldr/baselines/mldr_en_original/eval_summary.json

@@ -0,0 +1,21 @@
+{
+  "input_dataset": "/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/mldr_runs/open-provence-reranker-v1/mldr_en_original/process_original/dataset",
+  "language": "en",
+  "llm_model": "gpt-5-nano",
+  "reasoning_effort": "low",
+  "records_evaluated": 174,
+  "ignored_count": 208,
+  "counts": {
+    "has_answer_1": 163,
+    "has_answer_0": 11,
+    "failed": 0
+  },
+  "answer_score_stats": {
+    "mean": 0.9281034482758621,
+    "median": 1.0,
+    "min": 0.0,
+    "max": 1.0
+  },
+  "process_time_seconds": 3.4119314670097083,
+  "evaluation_time_seconds": 98.81951962405583
+}

eval_results/mldr/baselines/mldr_en_original/eval_summary.md

@@ -0,0 +1,19 @@
+# LLM Evaluation Summary
+
+- Dataset: `/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/mldr_runs/open-provence-reranker-v1/mldr_en_original/process_original/dataset`
+- Language: en
+- LLM model: gpt-5-nano
+- Reasoning effort: low
+- Records evaluated: 174
+- Ignored queries: 208
+- Has answer (1): 163
+- Has answer (0): 11
+- Failed: 0
+- Process time (s): 3.41
+- LLM eval time (s): 98.82
+
+## Answer Score Statistics
+- mean: 0.9281
+- median: 1.0000
+- min: 0.0000
+- max: 1.0000

eval_results/mldr/baselines/mldr_ja_original/eval_summary.json

@@ -0,0 +1,21 @@
+{
+  "input_dataset": "/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/mldr_runs/open-provence-reranker-japanese-v1/mldr_ja_original/process_original/dataset",
+  "language": "jp",
+  "llm_model": "gpt-5-nano",
+  "reasoning_effort": "low",
+  "records_evaluated": 166,
+  "ignored_count": 272,
+  "counts": {
+    "has_answer_1": 129,
+    "has_answer_0": 37,
+    "failed": 0
+  },
+  "answer_score_stats": {
+    "mean": 0.734578313253012,
+    "median": 0.9,
+    "min": 0.0,
+    "max": 1.0
+  },
+  "process_time_seconds": 2.720734969014302,
+  "evaluation_time_seconds": 169.58438874501735
+}

eval_results/mldr/baselines/mldr_ja_original/eval_summary.md

@@ -0,0 +1,19 @@
+# LLM Evaluation Summary
+
+- Dataset: `/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/mldr_runs/open-provence-reranker-japanese-v1/mldr_ja_original/process_original/dataset`
+- Language: jp
+- LLM model: gpt-5-nano
+- Reasoning effort: low
+- Records evaluated: 166
+- Ignored queries: 272
+- Has answer (1): 129
+- Has answer (0): 37
+- Failed: 0
+- Process time (s): 2.72
+- LLM eval time (s): 169.58
+
+## Answer Score Statistics
+- mean: 0.7346
+- median: 0.9000
+- min: 0.0000
+- max: 1.0000

eval_results/mldr/baselines/naver-provence-reranker-debertav3-v1_mldr_en_th_0_05/eval_summary.json

@@ -0,0 +1,21 @@
+{
+  "input_dataset": "/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/naver-provence-reranker-eval/naver-provence-reranker-debertav3-v1_mldr_en_th_0_05/run1/process/dataset",
+  "language": "en",
+  "llm_model": "gpt-5-nano",
+  "reasoning_effort": "low",
+  "records_evaluated": 174,
+  "ignored_count": 208,
+  "counts": {
+    "has_answer_1": 162,
+    "has_answer_0": 12,
+    "failed": 0
+  },
+  "answer_score_stats": {
+    "mean": 0.9173563218390804,
+    "median": 1.0,
+    "min": 0.0,
+    "max": 1.0
+  },
+  "process_time_seconds": 380.79417042899877,
+  "evaluation_time_seconds": 29.97553447500104
+}

eval_results/mldr/baselines/naver-provence-reranker-debertav3-v1_mldr_en_th_0_05/eval_summary.md

@@ -0,0 +1,19 @@
+# LLM Evaluation Summary
+
+- Dataset: `/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/naver-provence-reranker-eval/naver-provence-reranker-debertav3-v1_mldr_en_th_0_05/run1/process/dataset`
+- Language: en
+- LLM model: gpt-5-nano
+- Reasoning effort: low
+- Records evaluated: 174
+- Ignored queries: 208
+- Has answer (1): 162
+- Has answer (0): 12
+- Failed: 0
+- Process time (s): 380.79
+- LLM eval time (s): 29.98
+
+## Answer Score Statistics
+- mean: 0.9174
+- median: 1.0000
+- min: 0.0000
+- max: 1.0000

eval_results/mldr/baselines/naver-provence-reranker-debertav3-v1_mldr_en_th_0_05/process_summary.json

@@ -0,0 +1,17 @@
+{
+  "limit": 200,
+  "threshold": 0.05,
+  "num_records": 1600,
+  "num_queries": 200,
+  "dataset_language": "en",
+  "splitter_language": "en",
+  "max_length": null,
+  "model": "naver/provence-reranker-debertav3-v1",
+  "naver_provence_model": true,
+  "avg_pos_score": -6.5308984375,
+  "avg_neg_score": -10.574609375,
+  "avg_pos_compression": 92.10123209994308,
+  "avg_neg_compression": 99.15497159939561,
+  "source_text": "pruned",
+  "process_time_seconds": 380.79417042899877
+}

eval_results/mldr/baselines/naver-provence-reranker-debertav3-v1_mldr_en_th_0_1/eval_summary.json

@@ -0,0 +1,21 @@
+{
+  "input_dataset": "/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/naver-provence-reranker-eval/naver-provence-reranker-debertav3-v1_mldr_en_th_0_1/process/dataset",
+  "language": "en",
+  "llm_model": "gpt-5-nano",
+  "reasoning_effort": "low",
+  "records_evaluated": 174,
+  "ignored_count": 208,
+  "counts": {
+    "has_answer_1": 162,
+    "has_answer_0": 12,
+    "failed": 0
+  },
+  "answer_score_stats": {
+    "mean": 0.9153448275862069,
+    "median": 1.0,
+    "min": 0.0,
+    "max": 1.0
+  },
+  "process_time_seconds": 389.7323627329897,
+  "evaluation_time_seconds": 190.08830377610866
+}

eval_results/mldr/baselines/naver-provence-reranker-debertav3-v1_mldr_en_th_0_1/eval_summary.md

@@ -0,0 +1,19 @@
+# LLM Evaluation Summary
+
+- Dataset: `/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/naver-provence-reranker-eval/naver-provence-reranker-debertav3-v1_mldr_en_th_0_1/process/dataset`
+- Language: en
+- LLM model: gpt-5-nano
+- Reasoning effort: low
+- Records evaluated: 174
+- Ignored queries: 208
+- Has answer (1): 162
+- Has answer (0): 12
+- Failed: 0
+- Process time (s): 389.73
+- LLM eval time (s): 190.09
+
+## Answer Score Statistics
+- mean: 0.9153
+- median: 1.0000
+- min: 0.0000
+- max: 1.0000

eval_results/mldr/baselines/naver-provence-reranker-debertav3-v1_mldr_en_th_0_2/eval_summary.json

@@ -0,0 +1,21 @@
+{
+  "input_dataset": "/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/naver-provence-reranker-eval/naver-provence-reranker-debertav3-v1_mldr_en_th_0_2/process/dataset",
+  "language": "en",
+  "llm_model": "gpt-5-nano",
+  "reasoning_effort": "low",
+  "records_evaluated": 174,
+  "ignored_count": 208,
+  "counts": {
+    "has_answer_1": 157,
+    "has_answer_0": 17,
+    "failed": 0
+  },
+  "answer_score_stats": {
+    "mean": 0.8882758620689656,
+    "median": 1.0,
+    "min": 0.0,
+    "max": 1.0
+  },
+  "process_time_seconds": 392.35378917702474,
+  "evaluation_time_seconds": 187.29701190802734
+}

eval_results/mldr/baselines/naver-provence-reranker-debertav3-v1_mldr_en_th_0_2/eval_summary.md

@@ -0,0 +1,19 @@
+# LLM Evaluation Summary
+
+- Dataset: `/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/naver-provence-reranker-eval/naver-provence-reranker-debertav3-v1_mldr_en_th_0_2/process/dataset`
+- Language: en
+- LLM model: gpt-5-nano
+- Reasoning effort: low
+- Records evaluated: 174
+- Ignored queries: 208
+- Has answer (1): 157
+- Has answer (0): 17
+- Failed: 0
+- Process time (s): 392.35
+- LLM eval time (s): 187.30
+
+## Answer Score Statistics
+- mean: 0.8883
+- median: 1.0000
+- min: 0.0000
+- max: 1.0000

eval_results/mldr/baselines/naver-provence-reranker-debertav3-v1_mldr_en_th_0_5/eval_summary.json

@@ -0,0 +1,21 @@
+{
+  "input_dataset": "/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/naver-provence-reranker-eval/naver-provence-reranker-debertav3-v1_mldr_en_th_0_5/process/dataset",
+  "language": "en",
+  "llm_model": "gpt-5-nano",
+  "reasoning_effort": "low",
+  "records_evaluated": 174,
+  "ignored_count": 208,
+  "counts": {
+    "has_answer_1": 147,
+    "has_answer_0": 27,
+    "failed": 0
+  },
+  "answer_score_stats": {
+    "mean": 0.8420114942528735,
+    "median": 1.0,
+    "min": 0.0,
+    "max": 1.0
+  },
+  "process_time_seconds": 391.33639042195864,
+  "evaluation_time_seconds": 181.43732876703143
+}

eval_results/mldr/baselines/naver-provence-reranker-debertav3-v1_mldr_en_th_0_5/eval_summary.md

@@ -0,0 +1,19 @@
+# LLM Evaluation Summary
+
+- Dataset: `/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/naver-provence-reranker-eval/naver-provence-reranker-debertav3-v1_mldr_en_th_0_5/process/dataset`
+- Language: en
+- LLM model: gpt-5-nano
+- Reasoning effort: low
+- Records evaluated: 174
+- Ignored queries: 208
+- Has answer (1): 147
+- Has answer (0): 27
+- Failed: 0
+- Process time (s): 391.34
+- LLM eval time (s): 181.44
+
+## Answer Score Statistics
+- mean: 0.8420
+- median: 1.0000
+- min: 0.0000
+- max: 1.0000

eval_results/mldr/en_th_0_05/eval_summary.json

@@ -0,0 +1,21 @@
+{
+  "input_dataset": "/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/mldr_runs/open-provence-reranker-v1/en_th_0_05_attempt1/process/dataset",
+  "language": "en",
+  "llm_model": "gpt-5-nano",
+  "reasoning_effort": "low",
+  "records_evaluated": 174,
+  "ignored_count": 208,
+  "counts": {
+    "has_answer_1": 164,
+    "has_answer_0": 10,
+    "failed": 0
+  },
+  "answer_score_stats": {
+    "mean": 0.9278735632183908,
+    "median": 1.0,
+    "min": 0.0,
+    "max": 1.0
+  },
+  "process_time_seconds": 261.30367420602124,
+  "evaluation_time_seconds": 29.534542897017673
+}

eval_results/mldr/en_th_0_05/eval_summary.md

@@ -0,0 +1,19 @@
+# LLM Evaluation Summary
+
+- Dataset: `/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/mldr_runs/open-provence-reranker-v1/en_th_0_05_attempt1/process/dataset`
+- Language: en
+- LLM model: gpt-5-nano
+- Reasoning effort: low
+- Records evaluated: 174
+- Ignored queries: 208
+- Has answer (1): 164
+- Has answer (0): 10
+- Failed: 0
+- Process time (s): 261.30
+- LLM eval time (s): 29.53
+
+## Answer Score Statistics
+- mean: 0.9279
+- median: 1.0000
+- min: 0.0000
+- max: 1.0000

eval_results/mldr/en_th_0_05/process_summary.json

@@ -0,0 +1,17 @@
+{
+  "limit": 200,
+  "threshold": 0.05,
+  "num_records": 1600,
+  "num_queries": 200,
+  "dataset_language": "en",
+  "splitter_language": "auto",
+  "max_length": null,
+  "model": "output/release_models/open-provence-reranker-v1",
+  "naver_provence_model": false,
+  "avg_pos_score": 0.7220386701822281,
+  "avg_neg_score": 0.16591052538582257,
+  "avg_pos_compression": 86.67305848274736,
+  "avg_neg_compression": 99.71228029348991,
+  "source_text": "pruned",
+  "process_time_seconds": 261.30367420602124
+}

eval_results/mldr/en_th_0_1/eval_summary.json

@@ -0,0 +1,21 @@
+{
+  "input_dataset": "/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/mldr_runs/open-provence-reranker-v1/en_th_0_1_attempt1/process/dataset",
+  "language": "en",
+  "llm_model": "gpt-5-nano",
+  "reasoning_effort": "low",
+  "records_evaluated": 174,
+  "ignored_count": 208,
+  "counts": {
+    "has_answer_1": 164,
+    "has_answer_0": 10,
+    "failed": 0
+  },
+  "answer_score_stats": {
+    "mean": 0.9351149425287357,
+    "median": 1.0,
+    "min": 0.0,
+    "max": 1.0
+  },
+  "process_time_seconds": 260.8915817589732,
+  "evaluation_time_seconds": 31.940818482078612
+}

eval_results/mldr/en_th_0_1/eval_summary.md

@@ -0,0 +1,19 @@
+# LLM Evaluation Summary
+
+- Dataset: `/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/mldr_runs/open-provence-reranker-v1/en_th_0_1_attempt1/process/dataset`
+- Language: en
+- LLM model: gpt-5-nano
+- Reasoning effort: low
+- Records evaluated: 174
+- Ignored queries: 208
+- Has answer (1): 164
+- Has answer (0): 10
+- Failed: 0
+- Process time (s): 260.89
+- LLM eval time (s): 31.94
+
+## Answer Score Statistics
+- mean: 0.9351
+- median: 1.0000
+- min: 0.0000
+- max: 1.0000

eval_results/mldr/en_th_0_1/process_summary.json

@@ -0,0 +1,17 @@
+{
+  "limit": 200,
+  "threshold": 0.1,
+  "num_records": 1600,
+  "num_queries": 200,
+  "dataset_language": "en",
+  "splitter_language": "auto",
+  "max_length": null,
+  "model": "output/release_models/open-provence-reranker-v1",
+  "naver_provence_model": false,
+  "avg_pos_score": 0.7186262372136116,
+  "avg_neg_score": 0.10100883937307767,
+  "avg_pos_compression": 92.32767405509574,
+  "avg_neg_compression": 99.91221173248853,
+  "source_text": "pruned",
+  "process_time_seconds": 260.8915817589732
+}

eval_results/mldr/en_th_0_3/eval_summary.json

@@ -0,0 +1,21 @@
+{
+  "input_dataset": "/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/mldr_runs/open-provence-reranker-v1/en_th_0_3_attempt1/process/dataset",
+  "language": "en",
+  "llm_model": "gpt-5-nano",
+  "reasoning_effort": "low",
+  "records_evaluated": 174,
+  "ignored_count": 208,
+  "counts": {
+    "has_answer_1": 157,
+    "has_answer_0": 17,
+    "failed": 0
+  },
+  "answer_score_stats": {
+    "mean": 0.8953448275862068,
+    "median": 1.0,
+    "min": 0.0,
+    "max": 1.0
+  },
+  "process_time_seconds": 261.1759908599779,
+  "evaluation_time_seconds": 27.776169850025326
+}

eval_results/mldr/en_th_0_3/eval_summary.md

@@ -0,0 +1,19 @@
+# LLM Evaluation Summary
+
+- Dataset: `/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/mldr_runs/open-provence-reranker-v1/en_th_0_3_attempt1/process/dataset`
+- Language: en
+- LLM model: gpt-5-nano
+- Reasoning effort: low
+- Records evaluated: 174
+- Ignored queries: 208
+- Has answer (1): 157
+- Has answer (0): 17
+- Failed: 0
+- Process time (s): 261.18
+- LLM eval time (s): 27.78
+
+## Answer Score Statistics
+- mean: 0.8953
+- median: 1.0000
+- min: 0.0000
+- max: 1.0000

eval_results/mldr/en_th_0_3/process_summary.json

@@ -0,0 +1,17 @@
+{
+  "limit": 200,
+  "threshold": 0.3,
+  "num_records": 1600,
+  "num_queries": 200,
+  "dataset_language": "en",
+  "splitter_language": "auto",
+  "max_length": null,
+  "model": "output/release_models/open-provence-reranker-v1",
+  "naver_provence_model": false,
+  "avg_pos_score": 0.715216779410839,
+  "avg_neg_score": 0.02076476133295468,
+  "avg_pos_compression": 96.97861135663942,
+  "avg_neg_compression": 99.993944709442,
+  "source_text": "pruned",
+  "process_time_seconds": 261.1759908599779
+}

eval_results/mldr/en_th_0_5/eval_summary.json

@@ -0,0 +1,21 @@
+{
+  "input_dataset": "/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/mldr_runs/open-provence-reranker-v1/en_th_0_5_attempt1/process/dataset",
+  "language": "en",
+  "llm_model": "gpt-5-nano",
+  "reasoning_effort": "low",
+  "records_evaluated": 174,
+  "ignored_count": 208,
+  "counts": {
+    "has_answer_1": 152,
+    "has_answer_0": 22,
+    "failed": 0
+  },
+  "answer_score_stats": {
+    "mean": 0.8660919540229884,
+    "median": 1.0,
+    "min": 0.0,
+    "max": 1.0
+  },
+  "process_time_seconds": 261.31356202194,
+  "evaluation_time_seconds": 25.42166205099784
+}

eval_results/mldr/en_th_0_5/eval_summary.md

@@ -0,0 +1,19 @@
+# LLM Evaluation Summary
+
+- Dataset: `/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/mldr_runs/open-provence-reranker-v1/en_th_0_5_attempt1/process/dataset`
+- Language: en
+- LLM model: gpt-5-nano
+- Reasoning effort: low
+- Records evaluated: 174
+- Ignored queries: 208
+- Has answer (1): 152
+- Has answer (0): 22
+- Failed: 0
+- Process time (s): 261.31
+- LLM eval time (s): 25.42
+
+## Answer Score Statistics
+- mean: 0.8661
+- median: 1.0000
+- min: 0.0000
+- max: 1.0000

eval_results/mldr/en_th_0_5/process_summary.json

@@ -0,0 +1,17 @@
+{
+  "limit": 200,
+  "threshold": 0.5,
+  "num_records": 1600,
+  "num_queries": 200,
+  "dataset_language": "en",
+  "splitter_language": "auto",
+  "max_length": null,
+  "model": "output/release_models/open-provence-reranker-v1",
+  "naver_provence_model": false,
+  "avg_pos_score": 0.6940265846252441,
+  "avg_neg_score": 0.006882384909050805,
+  "avg_pos_compression": 98.24189101722801,
+  "avg_neg_compression": 99.99934651299124,
+  "source_text": "pruned",
+  "process_time_seconds": 261.31356202194
+}

eval_results/naver-provence-reranker-debertav3-v1_mldr_en_th_0_1.md

@@ -0,0 +1,17 @@
+# LLM Evaluation Summary
+
+- Dataset: `/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/mldr_runs/naver-provence-reranker-debertav3-v1/mldr_en_th_0_1/process/dataset`
+- Language: en
+- LLM model: gpt-5-mini
+- Reasoning effort: low
+- Records evaluated: 174
+- Ignored queries: 208
+- Has answer (1): 159
+- Has answer (0): 15
+- Failed: 0
+
+## Answer Score Statistics
+- mean: 0.9115
+- median: 1.0000
+- min: 0.0000
+- max: 1.0000

eval_results/naver-xprovence-reranker-bgem3-v1_mldr_en_th_0_3.md

@@ -0,0 +1,17 @@
+# LLM Evaluation Summary
+
+- Dataset: `/home/hotchpotch/src/github.com/hotchpotch/open_provence/tmp/mldr_runs/naver-xprovence-reranker-bgem3-v1/mldr_en_th_0_3/process/dataset`
+- Language: en
+- LLM model: gpt-5-mini
+- Reasoning effort: low
+- Records evaluated: 174
+- Ignored queries: 208
+- Has answer (1): 74
+- Has answer (0): 100
+- Failed: 0
+
+## Answer Score Statistics
+- mean: 0.4306
+- median: 0.0500
+- min: 0.0000
+- max: 1.0000

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eaba6f11f47c1d595b837d617effcbfe72b6a4adc9ce8fce58d1b59baabe4e6
+size 598444940

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,952 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50280": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50281": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50282": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50283": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50284": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50285": {
+      "content": "[unused0]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "[unused1]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "[unused2]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "[unused3]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "[unused4]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "[unused5]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "[unused6]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "[unused7]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "[unused8]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "[unused9]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50295": {
+      "content": "[unused10]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50296": {
+      "content": "[unused11]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50297": {
+      "content": "[unused12]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50298": {
+      "content": "[unused13]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50299": {
+      "content": "[unused14]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50300": {
+      "content": "[unused15]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50301": {
+      "content": "[unused16]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50302": {
+      "content": "[unused17]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50303": {
+      "content": "[unused18]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50304": {
+      "content": "[unused19]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50305": {
+      "content": "[unused20]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50306": {
+      "content": "[unused21]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50307": {
+      "content": "[unused22]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50308": {
+      "content": "[unused23]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50309": {
+      "content": "[unused24]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50310": {
+      "content": "[unused25]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50311": {
+      "content": "[unused26]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50312": {
+      "content": "[unused27]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50313": {
+      "content": "[unused28]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50314": {
+      "content": "[unused29]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50315": {
+      "content": "[unused30]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50316": {
+      "content": "[unused31]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50317": {
+      "content": "[unused32]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50318": {
+      "content": "[unused33]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50319": {
+      "content": "[unused34]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50320": {
+      "content": "[unused35]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50321": {
+      "content": "[unused36]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50322": {
+      "content": "[unused37]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50323": {
+      "content": "[unused38]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50324": {
+      "content": "[unused39]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50325": {
+      "content": "[unused40]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50326": {
+      "content": "[unused41]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50327": {
+      "content": "[unused42]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50328": {
+      "content": "[unused43]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50329": {
+      "content": "[unused44]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50330": {
+      "content": "[unused45]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50331": {
+      "content": "[unused46]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50332": {
+      "content": "[unused47]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50333": {
+      "content": "[unused48]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50334": {
+      "content": "[unused49]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50335": {
+      "content": "[unused50]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50336": {
+      "content": "[unused51]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50337": {
+      "content": "[unused52]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50338": {
+      "content": "[unused53]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50339": {
+      "content": "[unused54]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50340": {
+      "content": "[unused55]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50341": {
+      "content": "[unused56]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50342": {
+      "content": "[unused57]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50343": {
+      "content": "[unused58]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50344": {
+      "content": "[unused59]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50345": {
+      "content": "[unused60]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50346": {
+      "content": "[unused61]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50347": {
+      "content": "[unused62]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50348": {
+      "content": "[unused63]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50349": {
+      "content": "[unused64]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50350": {
+      "content": "[unused65]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50351": {
+      "content": "[unused66]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50352": {
+      "content": "[unused67]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50353": {
+      "content": "[unused68]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50354": {
+      "content": "[unused69]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50355": {
+      "content": "[unused70]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50356": {
+      "content": "[unused71]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50357": {
+      "content": "[unused72]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50358": {
+      "content": "[unused73]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50359": {
+      "content": "[unused74]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50360": {
+      "content": "[unused75]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50361": {
+      "content": "[unused76]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50362": {
+      "content": "[unused77]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50363": {
+      "content": "[unused78]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50364": {
+      "content": "[unused79]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50365": {
+      "content": "[unused80]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50366": {
+      "content": "[unused81]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50367": {
+      "content": "[unused82]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.json

@@ -0,0 +1,200 @@
+{
+  "model_args": {
+    "model_name_or_path": "Alibaba-NLP/gte-reranker-modernbert-base",
+    "num_labels": null,
+    "classifier_dropout": 0.0,
+    "max_length": 512,
+    "config_name": null,
+    "tokenizer_name": null,
+    "cache_dir": null
+  },
+  "data_args": {
+    "dataset_name": "hotchpotch/wip-msmarco-context-relevance",
+    "subset": "msmarco-ja-minimal",
+    "teacher_column": null,
+    "datasets": [
+      {
+        "dataset_name": "hotchpotch/msmarco-context-relevance",
+        "subset": "freq2",
+        "teacher_column": "teacher_scores.gte-reranker-modernbert-base"
+      },
+      {
+        "dataset_name": "hotchpotch/natural-questions-context-relevance",
+        "subset": "nodup_freq2",
+        "teacher_column": "teacher_scores.gte-reranker-modernbert-base",
+        "items": 6
+      },
+      {
+        "dataset_name": "hotchpotch/gooaq-context-relevance-130k",
+        "subset": "default",
+        "teacher_column": "teacher_scores.gte-reranker-modernbert-base",
+        "items": 6
+      }
+    ],
+    "items": null,
+    "max_train_samples": null,
+    "max_eval_samples": null,
+    "validation_split": null,
+    "validation_split_samples": null,
+    "validation_split_name": "validation",
+    "preprocessing_num_workers": null,
+    "filter_zero_relevance_max_items": null,
+    "filter_zero_relevance_max_items_reverse": false,
+    "filter_keep_first_item": false,
+    "upsample_factor": null
+  },
+  "training_args": {
+    "output_dir": "./output/freq-open-provence-reranker-v1_20251027_092433",
+    "overwrite_output_dir": true,
+    "do_train": true,
+    "do_eval": true,
+    "do_predict": false,
+    "eval_strategy": "steps",
+    "prediction_loss_only": false,
+    "per_device_train_batch_size": 4,
+    "per_device_eval_batch_size": 16,
+    "per_gpu_train_batch_size": null,
+    "per_gpu_eval_batch_size": null,
+    "gradient_accumulation_steps": 64,
+    "eval_accumulation_steps": null,
+    "eval_delay": 0,
+    "torch_empty_cache_steps": null,
+    "learning_rate": 5e-05,
+    "weight_decay": 0.01,
+    "adam_beta1": 0.9,
+    "adam_beta2": 0.999,
+    "adam_epsilon": 1e-08,
+    "max_grad_norm": 1.0,
+    "num_train_epochs": 1,
+    "max_steps": -1,
+    "lr_scheduler_type": "cosine",
+    "lr_scheduler_kwargs": {},
+    "warmup_ratio": 0.1,
+    "warmup_steps": 0,
+    "log_level": "passive",
+    "log_level_replica": "warning",
+    "log_on_each_node": true,
+    "logging_dir": "trainer_output/runs/Oct27_09-24-33_yuix",
+    "logging_strategy": "steps",
+    "logging_first_step": false,
+    "logging_steps": 15,
+    "logging_nan_inf_filter": true,
+    "save_strategy": "steps",
+    "save_steps": 500,
+    "save_total_limit": 5,
+    "save_safetensors": true,
+    "save_on_each_node": false,
+    "save_only_model": false,
+    "restore_callback_states_from_checkpoint": false,
+    "no_cuda": false,
+    "use_cpu": false,
+    "use_mps_device": false,
+    "seed": 42,
+    "data_seed": null,
+    "jit_mode_eval": false,
+    "bf16": true,
+    "fp16": false,
+    "fp16_opt_level": "O1",
+    "half_precision_backend": "auto",
+    "bf16_full_eval": false,
+    "fp16_full_eval": false,
+    "tf32": null,
+    "local_rank": 0,
+    "ddp_backend": null,
+    "tpu_num_cores": null,
+    "tpu_metrics_debug": false,
+    "debug": [],
+    "dataloader_drop_last": false,
+    "eval_steps": 77,
+    "dataloader_num_workers": 8,
+    "dataloader_prefetch_factor": null,
+    "past_index": -1,
+    "run_name": "freq-open-provence-reranker-v1-20251027_092433",
+    "disable_tqdm": false,
+    "remove_unused_columns": false,
+    "label_names": null,
+    "load_best_model_at_end": true,
+    "metric_for_best_model": "eval_loss",
+    "greater_is_better": false,
+    "ignore_data_skip": false,
+    "fsdp": [],
+    "fsdp_min_num_params": 0,
+    "fsdp_config": {
+      "min_num_params": 0,
+      "xla": false,
+      "xla_fsdp_v2": false,
+      "xla_fsdp_grad_ckpt": false
+    },
+    "fsdp_transformer_layer_cls_to_wrap": null,
+    "accelerator_config": "AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False)",
+    "parallelism_config": null,
+    "deepspeed": null,
+    "label_smoothing_factor": 0.0,
+    "optim": "adafactor",
+    "optim_args": null,
+    "adafactor": false,
+    "group_by_length": false,
+    "length_column_name": "length",
+    "report_to": [
+      "wandb"
+    ],
+    "project": "huggingface",
+    "trackio_space_id": "trackio",
+    "ddp_find_unused_parameters": null,
+    "ddp_bucket_cap_mb": null,
+    "ddp_broadcast_buffers": null,
+    "dataloader_pin_memory": true,
+    "dataloader_persistent_workers": false,
+    "skip_memory_metrics": true,
+    "use_legacy_prediction_loop": false,
+    "push_to_hub": false,
+    "resume_from_checkpoint": null,
+    "hub_model_id": null,
+    "hub_strategy": "every_save",
+    "hub_token": null,
+    "hub_private_repo": null,
+    "hub_always_push": false,
+    "hub_revision": null,
+    "gradient_checkpointing": false,
+    "gradient_checkpointing_kwargs": null,
+    "include_inputs_for_metrics": false,
+    "include_for_metrics": [],
+    "eval_do_concat_batches": true,
+    "fp16_backend": "auto",
+    "push_to_hub_model_id": null,
+    "push_to_hub_organization": null,
+    "push_to_hub_token": null,
+    "mp_parameters": "",
+    "auto_find_batch_size": false,
+    "full_determinism": false,
+    "torchdynamo": null,
+    "ray_scope": "last",
+    "ddp_timeout": 1800,
+    "torch_compile": false,
+    "torch_compile_backend": null,
+    "torch_compile_mode": null,
+    "include_tokens_per_second": false,
+    "include_num_input_tokens_seen": "no",
+    "neftune_noise_alpha": null,
+    "optim_target_modules": null,
+    "batch_eval_metrics": false,
+    "eval_on_start": false,
+    "use_liger_kernel": false,
+    "liger_kernel_config": null,
+    "eval_use_gather_object": false,
+    "average_tokens_across_devices": true,
+    "ranking_weight": 0.05,
+    "pruning_weight": 1.0,
+    "use_teacher_scores": true,
+    "sentence_level_pruning": true,
+    "standalone_process_default_language": "en",
+    "eval_datasets": {
+      "config": "configs/eval_datasets/en.yaml",
+      "threshold": 0.1,
+      "batch_size": 32
+    },
+    "distributed_state": "Distributed environment: DistributedType.NO\nNum processes: 1\nProcess index: 0\nLocal process index: 0\nDevice: cuda\n",
+    "deepspeed_plugin": null,
+    "modeling_open_provence_default_language": "en"
+  }
+}